© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4305
    Prev
    Next
    INDEX
    Explanations

    legal litigation and adjudication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĦ¿
    -0.10
    oft
    -0.10
    -sama
    -0.09
    liness
    -0.09
    finder
    -0.09
    ä½ĵè´´
    -0.08
    OfWeek
    -0.08
    ìĶ¨
    -0.08
    OfMonth
    -0.08
    asar
    -0.08
    POSITIVE LOGITS
    亵
    0.10
    ging
    0.10
    ighting
    0.09
    ÑĢаÑĤ
    0.09
    ë§Ŀ
    0.09
    å°ı鸣
    0.09
    oster
    0.09
    鸨
    0.09
    éĻIJ
    0.09
    gable
    0.09
    Activations Density 0.009%

    No Known Activations